Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "Up"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.17
    ominator
    -0.16
    argon
    -0.16
    ì¡°
    -0.16
    atars
    -0.15
    ektor
    -0.15
    lectric
    -0.15
    erals
    -0.15
    uce
    -0.15
    eless
    -0.15
    POSITIVE LOGITS
    coming
    0.37
    ward
    0.36
    wards
    0.35
    stairs
    0.33
    graded
    0.31
    grades
    0.30
    grading
    0.29
    stream
    0.29
    dater
    0.28
    loading
    0.26
    Act Density 0.017%

    No Known Activations